A deep learning algorithm to improve readers’ interpretation and speed of pancreatic cystic lesions on dual-phase enhanced CT

• Published in: Abdominal imaging Vol. 47; no. 6; pp. 2135 - 2147
• Main Authors: Wang, Xiheng, Sun, Zhaoyong, Xue, Huadan, Qu, Taiping, Cheng, Sihang, Li, Juan, Li, Yatong, Mao, Li, Li, Xiuli, Zhu, Liang, Li, Xiao, Zhang, Longjing, Jin, Zhengyu, Yu, Yizhou
• Format: Journal Article
• Language: English
• Published: New York Springer US 01.06.2022; Springer Nature B.V
• Subjects: Accuracy; Algorithms; Computed tomography; Contrast media; Deep learning; Differential diagnosis; Differentiation; Feature extraction; Gastroenterology; Hepatology; Image enhancement; Imaging; Lesions; Machine learning; Medical diagnosis; Medicine; Medicine & Public Health; Pancreas; Radiology; Radiomics; Deep learning; Pancreatic cystic lesion; Computer-assisted; Diagnosis; Computed tomography
• DOI: 10.1007/s00261-022-03479-4
• ISSN: 2366-0058; 2366-004X

Purpose To develop a deep learning model (DLM) to improve readers’ interpretation and speed in the differentiation of pancreatic cystic lesions (PCLs) on dual-phase enhanced CT, and a low contrast media dose, external testing set validated the model. Materials and methods Dual-phase enhanced CT images of 363 patients with 368 PCLs obtained from two centers were retrospectively assessed. Based on the examination date, a training and validation set of 266 PCLs, an internal testing set of 52 PCLs were designated from center 1. An external testing set included 50 PCLs from center 2. Clinical and radiological characteristics were compared. The DLM was developed using 3D specially designed densely connected convolutional networks for PCL differentiation. Radiomic features were extracted to build a traditional radiomics model (RM). Performance of the DLM, traditional RM, and three readers was compared. Results The accuracy for differential diagnosis was 0.904 with DLM, which was the highest in the internal testing set. Accuracy differences between the DLM and senior radiologist were not significant both in the internal and external testing set (both p  > 0.05). With the help of the DLM, the accuracy and specificity of the junior radiologist were significantly improved (all p  < 0.05), and all readers’ diagnostic time was shortened (all p  < 0.05). Conclusion The DLM achieved senior radiologist-level performance in differentiating benign and malignant PCLs which could improve the junior radiologist’s interpretation and speed of PCLs on CT. Graphical abstract